Create readme.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- ar
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
+
tags:
|
| 7 |
+
- transformers
|
| 8 |
+
- sentence-transformers
|
| 9 |
+
- text-embeddings-inference
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Introducing ARM-V1 | Arabic Reranker Model (Version 1)
|
| 13 |
+
|
| 14 |
+
**For more info please refer to this blog: [ARM | Arabic Reranker Model](www.omarai.me).**
|
| 15 |
+
|
| 16 |
+
✨ This model is designed specifically for Arabic language reranking tasks, optimized to handle queries and passages with precision.
|
| 17 |
+
✨ Unlike embedding models, which generate vector representations, this reranker directly evaluates the similarity between a question and a document, outputting a relevance score.
|
| 18 |
+
✨ Trained on a combination of positive and hard negative query-passage pairs, it excels in identifying the most relevant results.
|
| 19 |
+
✨ The output score can be transformed into a [0, 1] range using a sigmoid function, providing a clear and interpretable measure of relevance.
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
|